Update app.py

app.py

@@ -5,50 +5,53 @@ import faiss
 from sentence_transformers import SentenceTransformer
 from transformers import pipeline
 
-# Load model for embeddings and QA generation
+# Load models for embeddings and generation
 embedder = SentenceTransformer('all-MiniLM-L6-v2')
 generator = pipeline("text2text-generation", model="facebook/bart-large")
 
-# Load your climate news dataset (title + description)
+# Load and combine train + test datasets
 @st.cache_data
 def load_data():
-  
+    train_df = pd.read_csv("train.csv")
+    test_df = pd.read_csv("test.csv")
+    df = pd.concat([train_df, test_df], ignore_index=True)
     df["text"] = df["title"].fillna('') + ". " + df["description"].fillna('')
     return df
 
-
+# Load the data
+df = load_data()
 corpus = df["text"].tolist()
 corpus_embeddings = embedder.encode(corpus, convert_to_tensor=True)
 
-# Build FAISS index for fast similarity search
+# Build FAISS index for similarity search
 index = faiss.IndexFlatL2(corpus_embeddings.shape[1])
 index.add(corpus_embeddings.cpu().detach().numpy())
 
+# App UI
 st.title("🧠 Climate News Fact Checker")
+st.markdown("Enter a **claim** to check if it's supported or refuted by recent climate-related news.")
 
-user_input = st.text_input("Enter a claim or statement to verify:")
+# User input
+user_input = st.text_input("🔎 Enter a claim or statement:")
 
 if user_input:
-    # Embed the user query
+    # Embed the input claim
     query_embedding = embedder.encode([user_input])
-    
-    # Search similar news articles
+
+    # Retrieve top-k similar news snippets
     top_k = 3
     D, I = index.search(query_embedding, top_k)
-    
-    # Get the top matched articles
     results = [corpus[i] for i in I[0]]
-    
-    # Display retrieved articles
-    st.subheader("🔍 Retrieved News Snippets")
+
+    # Show retrieved snippets
+    st.subheader("📄 Retrieved News Snippets")
     for idx, res in enumerate(results):
         st.write(f"**Snippet {idx+1}:** {res}")
-    
-    # Combine into context for generation
+
+    # Generate a response based on context
     context = " ".join(results)
     prompt = f"Claim: {user_input}\nContext: {context}\nAnswer:"
-    
-    # Generate answer
+
     st.subheader("✅ Fact Check Result")
     response = generator(prompt, max_length=100, do_sample=False)[0]['generated_text']
     st.write(response)